---
title: "Create image from text - Ideogram 4.5"
method: POST
path: "/v1/ai/text-to-image/ideogram-4-5"
tags: ["text-to-image"]
---

# Create image from text - Ideogram 4.5

`POST /v1/ai/text-to-image/ideogram-4-5`

## Request

- Base URL: `https://api.magnific.com`
- URL: `https://api.magnific.com/v1/ai/text-to-image/ideogram-4-5`
- Auth: API key in header `x-magnific-api-key`

Generate or edit images with Ideogram 4.5.

**Key Features:**
- Text-to-image and image editing in the same endpoint: send up to 5
  images; the first one is edited and the rest guide the edit
- Accurate text rendering for posters, logos and typography
- 13 aspect ratios at about 4 megapixels, plus `auto` to follow the
  input image

**Best for:**
- Designs with legible text, from scratch or from an existing image
- Instruction-based edits of an image guided by references

**Credits:** the price is set by `quality` (`very_low`, `low`, `medium` or
`high`). The other parameters do not affect it. `very_low` is only
available when images are sent.

## Request body

- TtiIdeogram45Request
  - `prompt` string, required: Text description of the image to generate, or of the edit to apply. When `images` are sent, refer to them by position: "image 1" is the first one (the image being edited) and "image 2" onwards are the references.
  - `webhook_url` string, uri: Optional callback URL that will receive asynchronous notifications whenever the task changes status. The payload sent to this URL is the same as the corresponding GET endpoint response, but without the data field.
  - `images` string[]: Optional input images. Without them the request is text-to-image. With them, the first image is the one being edited and the rest guide the edit as references. **Image requirements:** - Maximum 5 images - Supported formats: PNG, JPEG, WebP - Aspect ratio between 1:6 and 6:1 - Public HTTPS URL or base64-encoded string
  - `aspect_ratio` 'auto' | '1:1' | '4:5' | '5:4' | '3:4' | '4:3' | '2:3' | '3:2' | '9:16' | '16:9' | '1:2' | '2:1' | '1:3' | '3:1': Aspect ratio for the generated image, on a canvas of about 4 megapixels. **Available ratios:** - `auto`: Let the model choose (default). With `images` it follows the first image; without them it picks the canvas that best fits the prompt. - `1:1`: Square, 2048x2048 - `4:5`, `5:4`: Photo print - `3:4`, `4:3`: Standard - `2:3`, `3:2`: Classic photo - `9:16`, `16:9`: Social stories/Widescreen - `1:2`, `2:1`, `1:3`, `3:1`: Banners and vertical panels
  - `quality` 'very_low' | 'low' | 'medium' | 'high': Quality tier. It sets the price of the generation. **Available tiers:** - `very_low`: Cheapest and fastest. Only available when `images` are sent (editing); a text-only request with it is rejected. - `low` - `medium`: Default - `high`: Best quality, slowest
  - `magic_prompt` 'auto' | 'on' | 'off': Whether Ideogram's Magic Prompt rewrites the prompt into a more detailed one before generating. `auto` lets the model decide; use `off` for verbatim edit instructions. It does not affect the price.
  - `seed` integer: Seed for reproducible results. When omitted, a random seed is used.

## Response `200`

OK - The request has succeeded and the Ideogram 4.5 process has started.

- GetStyleTransferTaskStatus200Response
  - `data` TaskDetail, required
    - `task_id` string, uuid, required: Task identifier
    - `status` 'CREATED' | 'IN_PROGRESS' | 'COMPLETED' | 'FAILED', required: Task status
    - `generated` string[], required

## Other responses

- `400`: Bad Request - The server could not understand the request due to invalid syntax.
- `401`: Unauthorized - The client must authenticate itself to get the requested response.
- `500`: Internal Server Error - The server has encountered a situation it doesn't know how to handle.
- `503`: Service Unavailable

---

[API](https://skmtc.dev/magnific/apis/magnific-api.md) · [All operations](https://skmtc.dev/magnific/apis/magnific-api/llms.txt) · [OpenAPI document](https://skmtc.dev/magnific/apis/magnific-api/revisions/60711fb082c7?raw)